/[pcre]/code/trunk/pcre_tables.c
ViewVC logotype

Diff of /code/trunk/pcre_tables.c

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 236 by ph10, Tue Sep 11 12:57:06 2007 UTC revision 1015 by ph10, Sun Aug 26 16:07:14 2012 UTC
# Line 6  Line 6 
6  and semantics are as close as possible to those of the Perl 5 language.  and semantics are as close as possible to those of the Perl 5 language.
7    
8                         Written by Philip Hazel                         Written by Philip Hazel
9             Copyright (c) 1997-2007 University of Cambridge             Copyright (c) 1997-2012 University of Cambridge
10    
11  -----------------------------------------------------------------------------  -----------------------------------------------------------------------------
12  Redistribution and use in source and binary forms, with or without  Redistribution and use in source and binary forms, with or without
# Line 37  POSSIBILITY OF SUCH DAMAGE. Line 37  POSSIBILITY OF SUCH DAMAGE.
37  -----------------------------------------------------------------------------  -----------------------------------------------------------------------------
38  */  */
39    
40    #ifndef PCRE_INCLUDED
41    
42  /* This module contains some fixed tables that are used by more than one of the  /* This module contains some fixed tables that are used by more than one of the
43  PCRE code modules. The tables are also #included by the pcretest program, which  PCRE code modules. The tables are also #included by the pcretest program, which
# Line 50  clashes with the library. */ Line 51  clashes with the library. */
51    
52  #include "pcre_internal.h"  #include "pcre_internal.h"
53    
54    #endif /* PCRE_INCLUDED */
55    
56  /* Table of sizes for the fixed-length opcodes. It's defined in a macro so that  /* Table of sizes for the fixed-length opcodes. It's defined in a macro so that
57  the definition is next to the definition of the opcodes in pcre_internal.h. */  the definition is next to the definition of the opcodes in pcre_internal.h. */
58    
59  const uschar _pcre_OP_lengths[] = { OP_LENGTHS };  const pcre_uint8 PRIV(OP_lengths)[] = { OP_LENGTHS };
60    
61    
62    
# Line 65  const uschar _pcre_OP_lengths[] = { OP_L Line 67  const uschar _pcre_OP_lengths[] = { OP_L
67  /* These are the breakpoints for different numbers of bytes in a UTF-8  /* These are the breakpoints for different numbers of bytes in a UTF-8
68  character. */  character. */
69    
70  #ifdef SUPPORT_UTF8  #if (defined SUPPORT_UTF && defined COMPILE_PCRE8) \
71      || (defined PCRE_INCLUDED && defined SUPPORT_PCRE16)
72    
73  const int _pcre_utf8_table1[] =  /* These tables are also required by pcretest in 16 bit mode. */
74    
75    const int PRIV(utf8_table1)[] =
76    { 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff};    { 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff};
77    
78  const int _pcre_utf8_table1_size = sizeof(_pcre_utf8_table1)/sizeof(int);  const int PRIV(utf8_table1_size) = sizeof(PRIV(utf8_table1)) / sizeof(int);
79    
80  /* These are the indicator bits and the mask for the data bits to set in the  /* These are the indicator bits and the mask for the data bits to set in the
81  first byte of a character, indexed by the number of additional bytes. */  first byte of a character, indexed by the number of additional bytes. */
82    
83  const int _pcre_utf8_table2[] = { 0,    0xc0, 0xe0, 0xf0, 0xf8, 0xfc};  const int PRIV(utf8_table2)[] = { 0,    0xc0, 0xe0, 0xf0, 0xf8, 0xfc};
84  const int _pcre_utf8_table3[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01};  const int PRIV(utf8_table3)[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01};
85    
86  /* Table of the number of extra bytes, indexed by the first byte masked with  /* Table of the number of extra bytes, indexed by the first byte masked with
87  0x3f. The highest number for a valid UTF-8 first byte is in fact 0x3d. */  0x3f. The highest number for a valid UTF-8 first byte is in fact 0x3d. */
88    
89  const uschar _pcre_utf8_table4[] = {  const pcre_uint8 PRIV(utf8_table4)[] = {
90    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
91    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
92    2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,    2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
93    3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 };    3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 };
94    
95  /* This table translates Unicode property names into type and code values. It  #endif /* (SUPPORT_UTF && COMPILE_PCRE8) || (PCRE_INCLUDED && SUPPORT_PCRE16)*/
96  is searched by binary chop, so must be in collating sequence of name. */  
97    #ifdef SUPPORT_UTF
98    
99    /* Table to translate from particular type value to the general value. */
100    
101    const int PRIV(ucp_gentype)[] = {
102      ucp_C, ucp_C, ucp_C, ucp_C, ucp_C,  /* Cc, Cf, Cn, Co, Cs */
103      ucp_L, ucp_L, ucp_L, ucp_L, ucp_L,  /* Ll, Lu, Lm, Lo, Lt */
104      ucp_M, ucp_M, ucp_M,                /* Mc, Me, Mn */
105      ucp_N, ucp_N, ucp_N,                /* Nd, Nl, No */
106      ucp_P, ucp_P, ucp_P, ucp_P, ucp_P,  /* Pc, Pd, Pe, Pf, Pi */
107      ucp_P, ucp_P,                       /* Ps, Po */
108      ucp_S, ucp_S, ucp_S, ucp_S,         /* Sc, Sk, Sm, So */
109      ucp_Z, ucp_Z, ucp_Z                 /* Zl, Zp, Zs */
110    };
111    
112    /* This table encodes the rules for finding the end of an extended grapheme
113    cluster. Every code point has a grapheme break property which is one of the
114    ucp_gbXX values defined in ucp.h. The 2-dimensional table is indexed by the
115    properties of two adjacent code points. The left property selects a word from
116    the table, and the right property selects a bit from that word like this:
117    
118      ucp_gbtable[left-property] & (1 << right-property)
119    
120    The value is non-zero if a grapheme break is NOT permitted between the relevant
121    two code points. The breaking rules are as follows:
122    
123    1. Break at the start and end of text (pretty obviously).
124    
125    2. Do not break between a CR and LF; otherwise, break before and   after
126       controls.
127    
128    3. Do not break Hangul syllable sequences, the rules for which are:
129    
130        L may be followed by L, V, LV or LVT
131        LV or V may be followed by V or T
132        LVT or T may be followed by T
133    
134    4. Do not break before extending characters.
135    
136    The next two rules are only for extended grapheme clusters (but that's what we
137    are implementing).
138    
139    5. Do not break before SpacingMarks.
140    
141    6. Do not break after Prepend characters.
142    
143    7. Otherwise, break everywhere.
144    */
145    
146    const pcre_uint32 PRIV(ucp_gbtable[]) = {
147       (1<<ucp_gbLF),                                           /*  0 CR */
148       0,                                                       /*  1 LF */
149       0,                                                       /*  2 Control */
150       (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark),                /*  3 Extend */
151       (1<<ucp_gbExtend)|(1<<ucp_gbPrepend)|                    /*  4 Prepend */
152         (1<<ucp_gbSpacingMark)|(1<<ucp_gbL)|
153         (1<<ucp_gbV)|(1<<ucp_gbT)|(1<<ucp_gbLV)|
154         (1<<ucp_gbLVT)|(1<<ucp_gbOther),
155    
156       (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark),                /*  5 SpacingMark */
157       (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbL)|   /*  6 L */
158         (1<<ucp_gbL)|(1<<ucp_gbV)|(1<<ucp_gbLV)|(1<<ucp_gbLVT),
159    
160       (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbV)|   /*  7 V */
161         (1<<ucp_gbT),
162    
163       (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbT),   /*  8 T */
164       (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbV)|   /*  9 LV */
165         (1<<ucp_gbT),
166    
167       (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbT),   /* 10 LVT */
168       (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)                 /* 11 Other */
169    };
170    
171    #ifdef SUPPORT_JIT
172    /* This table reverses PRIV(ucp_gentype). We can save the cost
173    of a memory load. */
174    
175    const int PRIV(ucp_typerange)[] = {
176      ucp_Cc, ucp_Cs,
177      ucp_Ll, ucp_Lu,
178      ucp_Mc, ucp_Mn,
179      ucp_Nd, ucp_No,
180      ucp_Pc, ucp_Ps,
181      ucp_Sc, ucp_So,
182      ucp_Zl, ucp_Zs,
183    };
184    #endif /* SUPPORT_JIT */
185    
186  const ucp_type_table _pcre_utt[] = {  /* The pcre_utt[] table below translates Unicode property names into type and
187    { "Any",                 PT_ANY,  0 },  code values. It is searched by binary chop, so must be in collating sequence of
188    { "Arabic",              PT_SC,   ucp_Arabic },  name. Originally, the table contained pointers to the name strings in the first
189    { "Armenian",            PT_SC,   ucp_Armenian },  field of each entry. However, that leads to a large number of relocations when
190    { "Balinese",            PT_SC,   ucp_Balinese },  a shared library is dynamically loaded. A significant reduction is made by
191    { "Bengali",             PT_SC,   ucp_Bengali },  putting all the names into a single, large string and then using offsets in the
192    { "Bopomofo",            PT_SC,   ucp_Bopomofo },  table itself. Maintenance is more error-prone, but frequent changes to this
193    { "Braille",             PT_SC,   ucp_Braille },  data are unlikely.
194    { "Buginese",            PT_SC,   ucp_Buginese },  
195    { "Buhid",               PT_SC,   ucp_Buhid },  July 2008: There is now a script called maint/GenerateUtt.py that can be used
196    { "C",                   PT_GC,   ucp_C },  to generate this data automatically instead of maintaining it by hand.
197    { "Canadian_Aboriginal", PT_SC,   ucp_Canadian_Aboriginal },  
198    { "Cc",                  PT_PC,   ucp_Cc },  The script was updated in March 2009 to generate a new EBCDIC-compliant
199    { "Cf",                  PT_PC,   ucp_Cf },  version. Like all other character and string literals that are compared against
200    { "Cherokee",            PT_SC,   ucp_Cherokee },  the regular expression pattern, we must use STR_ macros instead of literal
201    { "Cn",                  PT_PC,   ucp_Cn },  strings to make sure that UTF-8 support works on EBCDIC platforms. */
202    { "Co",                  PT_PC,   ucp_Co },  
203    { "Common",              PT_SC,   ucp_Common },  #define STRING_Any0 STR_A STR_n STR_y "\0"
204    { "Coptic",              PT_SC,   ucp_Coptic },  #define STRING_Arabic0 STR_A STR_r STR_a STR_b STR_i STR_c "\0"
205    { "Cs",                  PT_PC,   ucp_Cs },  #define STRING_Armenian0 STR_A STR_r STR_m STR_e STR_n STR_i STR_a STR_n "\0"
206    { "Cuneiform",           PT_SC,   ucp_Cuneiform },  #define STRING_Avestan0 STR_A STR_v STR_e STR_s STR_t STR_a STR_n "\0"
207    { "Cypriot",             PT_SC,   ucp_Cypriot },  #define STRING_Balinese0 STR_B STR_a STR_l STR_i STR_n STR_e STR_s STR_e "\0"
208    { "Cyrillic",            PT_SC,   ucp_Cyrillic },  #define STRING_Bamum0 STR_B STR_a STR_m STR_u STR_m "\0"
209    { "Deseret",             PT_SC,   ucp_Deseret },  #define STRING_Batak0 STR_B STR_a STR_t STR_a STR_k "\0"
210    { "Devanagari",          PT_SC,   ucp_Devanagari },  #define STRING_Bengali0 STR_B STR_e STR_n STR_g STR_a STR_l STR_i "\0"
211    { "Ethiopic",            PT_SC,   ucp_Ethiopic },  #define STRING_Bopomofo0 STR_B STR_o STR_p STR_o STR_m STR_o STR_f STR_o "\0"
212    { "Georgian",            PT_SC,   ucp_Georgian },  #define STRING_Brahmi0 STR_B STR_r STR_a STR_h STR_m STR_i "\0"
213    { "Glagolitic",          PT_SC,   ucp_Glagolitic },  #define STRING_Braille0 STR_B STR_r STR_a STR_i STR_l STR_l STR_e "\0"
214    { "Gothic",              PT_SC,   ucp_Gothic },  #define STRING_Buginese0 STR_B STR_u STR_g STR_i STR_n STR_e STR_s STR_e "\0"
215    { "Greek",               PT_SC,   ucp_Greek },  #define STRING_Buhid0 STR_B STR_u STR_h STR_i STR_d "\0"
216    { "Gujarati",            PT_SC,   ucp_Gujarati },  #define STRING_C0 STR_C "\0"
217    { "Gurmukhi",            PT_SC,   ucp_Gurmukhi },  #define STRING_Canadian_Aboriginal0 STR_C STR_a STR_n STR_a STR_d STR_i STR_a STR_n STR_UNDERSCORE STR_A STR_b STR_o STR_r STR_i STR_g STR_i STR_n STR_a STR_l "\0"
218    { "Han",                 PT_SC,   ucp_Han },  #define STRING_Carian0 STR_C STR_a STR_r STR_i STR_a STR_n "\0"
219    { "Hangul",              PT_SC,   ucp_Hangul },  #define STRING_Cc0 STR_C STR_c "\0"
220    { "Hanunoo",             PT_SC,   ucp_Hanunoo },  #define STRING_Cf0 STR_C STR_f "\0"
221    { "Hebrew",              PT_SC,   ucp_Hebrew },  #define STRING_Chakma0 STR_C STR_h STR_a STR_k STR_m STR_a "\0"
222    { "Hiragana",            PT_SC,   ucp_Hiragana },  #define STRING_Cham0 STR_C STR_h STR_a STR_m "\0"
223    { "Inherited",           PT_SC,   ucp_Inherited },  #define STRING_Cherokee0 STR_C STR_h STR_e STR_r STR_o STR_k STR_e STR_e "\0"
224    { "Kannada",             PT_SC,   ucp_Kannada },  #define STRING_Cn0 STR_C STR_n "\0"
225    { "Katakana",            PT_SC,   ucp_Katakana },  #define STRING_Co0 STR_C STR_o "\0"
226    { "Kharoshthi",          PT_SC,   ucp_Kharoshthi },  #define STRING_Common0 STR_C STR_o STR_m STR_m STR_o STR_n "\0"
227    { "Khmer",               PT_SC,   ucp_Khmer },  #define STRING_Coptic0 STR_C STR_o STR_p STR_t STR_i STR_c "\0"
228    { "L",                   PT_GC,   ucp_L },  #define STRING_Cs0 STR_C STR_s "\0"
229    { "L&",                  PT_LAMP, 0 },  #define STRING_Cuneiform0 STR_C STR_u STR_n STR_e STR_i STR_f STR_o STR_r STR_m "\0"
230    { "Lao",                 PT_SC,   ucp_Lao },  #define STRING_Cypriot0 STR_C STR_y STR_p STR_r STR_i STR_o STR_t "\0"
231    { "Latin",               PT_SC,   ucp_Latin },  #define STRING_Cyrillic0 STR_C STR_y STR_r STR_i STR_l STR_l STR_i STR_c "\0"
232    { "Limbu",               PT_SC,   ucp_Limbu },  #define STRING_Deseret0 STR_D STR_e STR_s STR_e STR_r STR_e STR_t "\0"
233    { "Linear_B",            PT_SC,   ucp_Linear_B },  #define STRING_Devanagari0 STR_D STR_e STR_v STR_a STR_n STR_a STR_g STR_a STR_r STR_i "\0"
234    { "Ll",                  PT_PC,   ucp_Ll },  #define STRING_Egyptian_Hieroglyphs0 STR_E STR_g STR_y STR_p STR_t STR_i STR_a STR_n STR_UNDERSCORE STR_H STR_i STR_e STR_r STR_o STR_g STR_l STR_y STR_p STR_h STR_s "\0"
235    { "Lm",                  PT_PC,   ucp_Lm },  #define STRING_Ethiopic0 STR_E STR_t STR_h STR_i STR_o STR_p STR_i STR_c "\0"
236    { "Lo",                  PT_PC,   ucp_Lo },  #define STRING_Georgian0 STR_G STR_e STR_o STR_r STR_g STR_i STR_a STR_n "\0"
237    { "Lt",                  PT_PC,   ucp_Lt },  #define STRING_Glagolitic0 STR_G STR_l STR_a STR_g STR_o STR_l STR_i STR_t STR_i STR_c "\0"
238    { "Lu",                  PT_PC,   ucp_Lu },  #define STRING_Gothic0 STR_G STR_o STR_t STR_h STR_i STR_c "\0"
239    { "M",                   PT_GC,   ucp_M },  #define STRING_Greek0 STR_G STR_r STR_e STR_e STR_k "\0"
240    { "Malayalam",           PT_SC,   ucp_Malayalam },  #define STRING_Gujarati0 STR_G STR_u STR_j STR_a STR_r STR_a STR_t STR_i "\0"
241    { "Mc",                  PT_PC,   ucp_Mc },  #define STRING_Gurmukhi0 STR_G STR_u STR_r STR_m STR_u STR_k STR_h STR_i "\0"
242    { "Me",                  PT_PC,   ucp_Me },  #define STRING_Han0 STR_H STR_a STR_n "\0"
243    { "Mn",                  PT_PC,   ucp_Mn },  #define STRING_Hangul0 STR_H STR_a STR_n STR_g STR_u STR_l "\0"
244    { "Mongolian",           PT_SC,   ucp_Mongolian },  #define STRING_Hanunoo0 STR_H STR_a STR_n STR_u STR_n STR_o STR_o "\0"
245    { "Myanmar",             PT_SC,   ucp_Myanmar },  #define STRING_Hebrew0 STR_H STR_e STR_b STR_r STR_e STR_w "\0"
246    { "N",                   PT_GC,   ucp_N },  #define STRING_Hiragana0 STR_H STR_i STR_r STR_a STR_g STR_a STR_n STR_a "\0"
247    { "Nd",                  PT_PC,   ucp_Nd },  #define STRING_Imperial_Aramaic0 STR_I STR_m STR_p STR_e STR_r STR_i STR_a STR_l STR_UNDERSCORE STR_A STR_r STR_a STR_m STR_a STR_i STR_c "\0"
248    { "New_Tai_Lue",         PT_SC,   ucp_New_Tai_Lue },  #define STRING_Inherited0 STR_I STR_n STR_h STR_e STR_r STR_i STR_t STR_e STR_d "\0"
249    { "Nko",                 PT_SC,   ucp_Nko },  #define STRING_Inscriptional_Pahlavi0 STR_I STR_n STR_s STR_c STR_r STR_i STR_p STR_t STR_i STR_o STR_n STR_a STR_l STR_UNDERSCORE STR_P STR_a STR_h STR_l STR_a STR_v STR_i "\0"
250    { "Nl",                  PT_PC,   ucp_Nl },  #define STRING_Inscriptional_Parthian0 STR_I STR_n STR_s STR_c STR_r STR_i STR_p STR_t STR_i STR_o STR_n STR_a STR_l STR_UNDERSCORE STR_P STR_a STR_r STR_t STR_h STR_i STR_a STR_n "\0"
251    { "No",                  PT_PC,   ucp_No },  #define STRING_Javanese0 STR_J STR_a STR_v STR_a STR_n STR_e STR_s STR_e "\0"
252    { "Ogham",               PT_SC,   ucp_Ogham },  #define STRING_Kaithi0 STR_K STR_a STR_i STR_t STR_h STR_i "\0"
253    { "Old_Italic",          PT_SC,   ucp_Old_Italic },  #define STRING_Kannada0 STR_K STR_a STR_n STR_n STR_a STR_d STR_a "\0"
254    { "Old_Persian",         PT_SC,   ucp_Old_Persian },  #define STRING_Katakana0 STR_K STR_a STR_t STR_a STR_k STR_a STR_n STR_a "\0"
255    { "Oriya",               PT_SC,   ucp_Oriya },  #define STRING_Kayah_Li0 STR_K STR_a STR_y STR_a STR_h STR_UNDERSCORE STR_L STR_i "\0"
256    { "Osmanya",             PT_SC,   ucp_Osmanya },  #define STRING_Kharoshthi0 STR_K STR_h STR_a STR_r STR_o STR_s STR_h STR_t STR_h STR_i "\0"
257    { "P",                   PT_GC,   ucp_P },  #define STRING_Khmer0 STR_K STR_h STR_m STR_e STR_r "\0"
258    { "Pc",                  PT_PC,   ucp_Pc },  #define STRING_L0 STR_L "\0"
259    { "Pd",                  PT_PC,   ucp_Pd },  #define STRING_L_AMPERSAND0 STR_L STR_AMPERSAND "\0"
260    { "Pe",                  PT_PC,   ucp_Pe },  #define STRING_Lao0 STR_L STR_a STR_o "\0"
261    { "Pf",                  PT_PC,   ucp_Pf },  #define STRING_Latin0 STR_L STR_a STR_t STR_i STR_n "\0"
262    { "Phags_Pa",            PT_SC,   ucp_Phags_Pa },  #define STRING_Lepcha0 STR_L STR_e STR_p STR_c STR_h STR_a "\0"
263    { "Phoenician",          PT_SC,   ucp_Phoenician },  #define STRING_Limbu0 STR_L STR_i STR_m STR_b STR_u "\0"
264    { "Pi",                  PT_PC,   ucp_Pi },  #define STRING_Linear_B0 STR_L STR_i STR_n STR_e STR_a STR_r STR_UNDERSCORE STR_B "\0"
265    { "Po",                  PT_PC,   ucp_Po },  #define STRING_Lisu0 STR_L STR_i STR_s STR_u "\0"
266    { "Ps",                  PT_PC,   ucp_Ps },  #define STRING_Ll0 STR_L STR_l "\0"
267    { "Runic",               PT_SC,   ucp_Runic },  #define STRING_Lm0 STR_L STR_m "\0"
268    { "S",                   PT_GC,   ucp_S },  #define STRING_Lo0 STR_L STR_o "\0"
269    { "Sc",                  PT_PC,   ucp_Sc },  #define STRING_Lt0 STR_L STR_t "\0"
270    { "Shavian",             PT_SC,   ucp_Shavian },  #define STRING_Lu0 STR_L STR_u "\0"
271    { "Sinhala",             PT_SC,   ucp_Sinhala },  #define STRING_Lycian0 STR_L STR_y STR_c STR_i STR_a STR_n "\0"
272    { "Sk",                  PT_PC,   ucp_Sk },  #define STRING_Lydian0 STR_L STR_y STR_d STR_i STR_a STR_n "\0"
273    { "Sm",                  PT_PC,   ucp_Sm },  #define STRING_M0 STR_M "\0"
274    { "So",                  PT_PC,   ucp_So },  #define STRING_Malayalam0 STR_M STR_a STR_l STR_a STR_y STR_a STR_l STR_a STR_m "\0"
275    { "Syloti_Nagri",        PT_SC,   ucp_Syloti_Nagri },  #define STRING_Mandaic0 STR_M STR_a STR_n STR_d STR_a STR_i STR_c "\0"
276    { "Syriac",              PT_SC,   ucp_Syriac },  #define STRING_Mc0 STR_M STR_c "\0"
277    { "Tagalog",             PT_SC,   ucp_Tagalog },  #define STRING_Me0 STR_M STR_e "\0"
278    { "Tagbanwa",            PT_SC,   ucp_Tagbanwa },  #define STRING_Meetei_Mayek0 STR_M STR_e STR_e STR_t STR_e STR_i STR_UNDERSCORE STR_M STR_a STR_y STR_e STR_k "\0"
279    { "Tai_Le",              PT_SC,   ucp_Tai_Le },  #define STRING_Meroitic_Cursive0 STR_M STR_e STR_r STR_o STR_i STR_t STR_i STR_c STR_UNDERSCORE STR_C STR_u STR_r STR_s STR_i STR_v STR_e "\0"
280    { "Tamil",               PT_SC,   ucp_Tamil },  #define STRING_Meroitic_Hieroglyphs0 STR_M STR_e STR_r STR_o STR_i STR_t STR_i STR_c STR_UNDERSCORE STR_H STR_i STR_e STR_r STR_o STR_g STR_l STR_y STR_p STR_h STR_s "\0"
281    { "Telugu",              PT_SC,   ucp_Telugu },  #define STRING_Miao0 STR_M STR_i STR_a STR_o "\0"
282    { "Thaana",              PT_SC,   ucp_Thaana },  #define STRING_Mn0 STR_M STR_n "\0"
283    { "Thai",                PT_SC,   ucp_Thai },  #define STRING_Mongolian0 STR_M STR_o STR_n STR_g STR_o STR_l STR_i STR_a STR_n "\0"
284    { "Tibetan",             PT_SC,   ucp_Tibetan },  #define STRING_Myanmar0 STR_M STR_y STR_a STR_n STR_m STR_a STR_r "\0"
285    { "Tifinagh",            PT_SC,   ucp_Tifinagh },  #define STRING_N0 STR_N "\0"
286    { "Ugaritic",            PT_SC,   ucp_Ugaritic },  #define STRING_Nd0 STR_N STR_d "\0"
287    { "Yi",                  PT_SC,   ucp_Yi },  #define STRING_New_Tai_Lue0 STR_N STR_e STR_w STR_UNDERSCORE STR_T STR_a STR_i STR_UNDERSCORE STR_L STR_u STR_e "\0"
288    { "Z",                   PT_GC,   ucp_Z },  #define STRING_Nko0 STR_N STR_k STR_o "\0"
289    { "Zl",                  PT_PC,   ucp_Zl },  #define STRING_Nl0 STR_N STR_l "\0"
290    { "Zp",                  PT_PC,   ucp_Zp },  #define STRING_No0 STR_N STR_o "\0"
291    { "Zs",                  PT_PC,   ucp_Zs }  #define STRING_Ogham0 STR_O STR_g STR_h STR_a STR_m "\0"
292    #define STRING_Ol_Chiki0 STR_O STR_l STR_UNDERSCORE STR_C STR_h STR_i STR_k STR_i "\0"
293    #define STRING_Old_Italic0 STR_O STR_l STR_d STR_UNDERSCORE STR_I STR_t STR_a STR_l STR_i STR_c "\0"
294    #define STRING_Old_Persian0 STR_O STR_l STR_d STR_UNDERSCORE STR_P STR_e STR_r STR_s STR_i STR_a STR_n "\0"
295    #define STRING_Old_South_Arabian0 STR_O STR_l STR_d STR_UNDERSCORE STR_S STR_o STR_u STR_t STR_h STR_UNDERSCORE STR_A STR_r STR_a STR_b STR_i STR_a STR_n "\0"
296    #define STRING_Old_Turkic0 STR_O STR_l STR_d STR_UNDERSCORE STR_T STR_u STR_r STR_k STR_i STR_c "\0"
297    #define STRING_Oriya0 STR_O STR_r STR_i STR_y STR_a "\0"
298    #define STRING_Osmanya0 STR_O STR_s STR_m STR_a STR_n STR_y STR_a "\0"
299    #define STRING_P0 STR_P "\0"
300    #define STRING_Pc0 STR_P STR_c "\0"
301    #define STRING_Pd0 STR_P STR_d "\0"
302    #define STRING_Pe0 STR_P STR_e "\0"
303    #define STRING_Pf0 STR_P STR_f "\0"
304    #define STRING_Phags_Pa0 STR_P STR_h STR_a STR_g STR_s STR_UNDERSCORE STR_P STR_a "\0"
305    #define STRING_Phoenician0 STR_P STR_h STR_o STR_e STR_n STR_i STR_c STR_i STR_a STR_n "\0"
306    #define STRING_Pi0 STR_P STR_i "\0"
307    #define STRING_Po0 STR_P STR_o "\0"
308    #define STRING_Ps0 STR_P STR_s "\0"
309    #define STRING_Rejang0 STR_R STR_e STR_j STR_a STR_n STR_g "\0"
310    #define STRING_Runic0 STR_R STR_u STR_n STR_i STR_c "\0"
311    #define STRING_S0 STR_S "\0"
312    #define STRING_Samaritan0 STR_S STR_a STR_m STR_a STR_r STR_i STR_t STR_a STR_n "\0"
313    #define STRING_Saurashtra0 STR_S STR_a STR_u STR_r STR_a STR_s STR_h STR_t STR_r STR_a "\0"
314    #define STRING_Sc0 STR_S STR_c "\0"
315    #define STRING_Sharada0 STR_S STR_h STR_a STR_r STR_a STR_d STR_a "\0"
316    #define STRING_Shavian0 STR_S STR_h STR_a STR_v STR_i STR_a STR_n "\0"
317    #define STRING_Sinhala0 STR_S STR_i STR_n STR_h STR_a STR_l STR_a "\0"
318    #define STRING_Sk0 STR_S STR_k "\0"
319    #define STRING_Sm0 STR_S STR_m "\0"
320    #define STRING_So0 STR_S STR_o "\0"
321    #define STRING_Sora_Sompeng0 STR_S STR_o STR_r STR_a STR_UNDERSCORE STR_S STR_o STR_m STR_p STR_e STR_n STR_g "\0"
322    #define STRING_Sundanese0 STR_S STR_u STR_n STR_d STR_a STR_n STR_e STR_s STR_e "\0"
323    #define STRING_Syloti_Nagri0 STR_S STR_y STR_l STR_o STR_t STR_i STR_UNDERSCORE STR_N STR_a STR_g STR_r STR_i "\0"
324    #define STRING_Syriac0 STR_S STR_y STR_r STR_i STR_a STR_c "\0"
325    #define STRING_Tagalog0 STR_T STR_a STR_g STR_a STR_l STR_o STR_g "\0"
326    #define STRING_Tagbanwa0 STR_T STR_a STR_g STR_b STR_a STR_n STR_w STR_a "\0"
327    #define STRING_Tai_Le0 STR_T STR_a STR_i STR_UNDERSCORE STR_L STR_e "\0"
328    #define STRING_Tai_Tham0 STR_T STR_a STR_i STR_UNDERSCORE STR_T STR_h STR_a STR_m "\0"
329    #define STRING_Tai_Viet0 STR_T STR_a STR_i STR_UNDERSCORE STR_V STR_i STR_e STR_t "\0"
330    #define STRING_Takri0 STR_T STR_a STR_k STR_r STR_i "\0"
331    #define STRING_Tamil0 STR_T STR_a STR_m STR_i STR_l "\0"
332    #define STRING_Telugu0 STR_T STR_e STR_l STR_u STR_g STR_u "\0"
333    #define STRING_Thaana0 STR_T STR_h STR_a STR_a STR_n STR_a "\0"
334    #define STRING_Thai0 STR_T STR_h STR_a STR_i "\0"
335    #define STRING_Tibetan0 STR_T STR_i STR_b STR_e STR_t STR_a STR_n "\0"
336    #define STRING_Tifinagh0 STR_T STR_i STR_f STR_i STR_n STR_a STR_g STR_h "\0"
337    #define STRING_Ugaritic0 STR_U STR_g STR_a STR_r STR_i STR_t STR_i STR_c "\0"
338    #define STRING_Vai0 STR_V STR_a STR_i "\0"
339    #define STRING_Xan0 STR_X STR_a STR_n "\0"
340    #define STRING_Xps0 STR_X STR_p STR_s "\0"
341    #define STRING_Xsp0 STR_X STR_s STR_p "\0"
342    #define STRING_Xwd0 STR_X STR_w STR_d "\0"
343    #define STRING_Yi0 STR_Y STR_i "\0"
344    #define STRING_Z0 STR_Z "\0"
345    #define STRING_Zl0 STR_Z STR_l "\0"
346    #define STRING_Zp0 STR_Z STR_p "\0"
347    #define STRING_Zs0 STR_Z STR_s "\0"
348    
349    const char PRIV(utt_names)[] =
350      STRING_Any0
351      STRING_Arabic0
352      STRING_Armenian0
353      STRING_Avestan0
354      STRING_Balinese0
355      STRING_Bamum0
356      STRING_Batak0
357      STRING_Bengali0
358      STRING_Bopomofo0
359      STRING_Brahmi0
360      STRING_Braille0
361      STRING_Buginese0
362      STRING_Buhid0
363      STRING_C0
364      STRING_Canadian_Aboriginal0
365      STRING_Carian0
366      STRING_Cc0
367      STRING_Cf0
368      STRING_Chakma0
369      STRING_Cham0
370      STRING_Cherokee0
371      STRING_Cn0
372      STRING_Co0
373      STRING_Common0
374      STRING_Coptic0
375      STRING_Cs0
376      STRING_Cuneiform0
377      STRING_Cypriot0
378      STRING_Cyrillic0
379      STRING_Deseret0
380      STRING_Devanagari0
381      STRING_Egyptian_Hieroglyphs0
382      STRING_Ethiopic0
383      STRING_Georgian0
384      STRING_Glagolitic0
385      STRING_Gothic0
386      STRING_Greek0
387      STRING_Gujarati0
388      STRING_Gurmukhi0
389      STRING_Han0
390      STRING_Hangul0
391      STRING_Hanunoo0
392      STRING_Hebrew0
393      STRING_Hiragana0
394      STRING_Imperial_Aramaic0
395      STRING_Inherited0
396      STRING_Inscriptional_Pahlavi0
397      STRING_Inscriptional_Parthian0
398      STRING_Javanese0
399      STRING_Kaithi0
400      STRING_Kannada0
401      STRING_Katakana0
402      STRING_Kayah_Li0
403      STRING_Kharoshthi0
404      STRING_Khmer0
405      STRING_L0
406      STRING_L_AMPERSAND0
407      STRING_Lao0
408      STRING_Latin0
409      STRING_Lepcha0
410      STRING_Limbu0
411      STRING_Linear_B0
412      STRING_Lisu0
413      STRING_Ll0
414      STRING_Lm0
415      STRING_Lo0
416      STRING_Lt0
417      STRING_Lu0
418      STRING_Lycian0
419      STRING_Lydian0
420      STRING_M0
421      STRING_Malayalam0
422      STRING_Mandaic0
423      STRING_Mc0
424      STRING_Me0
425      STRING_Meetei_Mayek0
426      STRING_Meroitic_Cursive0
427      STRING_Meroitic_Hieroglyphs0
428      STRING_Miao0
429      STRING_Mn0
430      STRING_Mongolian0
431      STRING_Myanmar0
432      STRING_N0
433      STRING_Nd0
434      STRING_New_Tai_Lue0
435      STRING_Nko0
436      STRING_Nl0
437      STRING_No0
438      STRING_Ogham0
439      STRING_Ol_Chiki0
440      STRING_Old_Italic0
441      STRING_Old_Persian0
442      STRING_Old_South_Arabian0
443      STRING_Old_Turkic0
444      STRING_Oriya0
445      STRING_Osmanya0
446      STRING_P0
447      STRING_Pc0
448      STRING_Pd0
449      STRING_Pe0
450      STRING_Pf0
451      STRING_Phags_Pa0
452      STRING_Phoenician0
453      STRING_Pi0
454      STRING_Po0
455      STRING_Ps0
456      STRING_Rejang0
457      STRING_Runic0
458      STRING_S0
459      STRING_Samaritan0
460      STRING_Saurashtra0
461      STRING_Sc0
462      STRING_Sharada0
463      STRING_Shavian0
464      STRING_Sinhala0
465      STRING_Sk0
466      STRING_Sm0
467      STRING_So0
468      STRING_Sora_Sompeng0
469      STRING_Sundanese0
470      STRING_Syloti_Nagri0
471      STRING_Syriac0
472      STRING_Tagalog0
473      STRING_Tagbanwa0
474      STRING_Tai_Le0
475      STRING_Tai_Tham0
476      STRING_Tai_Viet0
477      STRING_Takri0
478      STRING_Tamil0
479      STRING_Telugu0
480      STRING_Thaana0
481      STRING_Thai0
482      STRING_Tibetan0
483      STRING_Tifinagh0
484      STRING_Ugaritic0
485      STRING_Vai0
486      STRING_Xan0
487      STRING_Xps0
488      STRING_Xsp0
489      STRING_Xwd0
490      STRING_Yi0
491      STRING_Z0
492      STRING_Zl0
493      STRING_Zp0
494      STRING_Zs0;
495    
496    const ucp_type_table PRIV(utt)[] = {
497      {   0, PT_ANY, 0 },
498      {   4, PT_SC, ucp_Arabic },
499      {  11, PT_SC, ucp_Armenian },
500      {  20, PT_SC, ucp_Avestan },
501      {  28, PT_SC, ucp_Balinese },
502      {  37, PT_SC, ucp_Bamum },
503      {  43, PT_SC, ucp_Batak },
504      {  49, PT_SC, ucp_Bengali },
505      {  57, PT_SC, ucp_Bopomofo },
506      {  66, PT_SC, ucp_Brahmi },
507      {  73, PT_SC, ucp_Braille },
508      {  81, PT_SC, ucp_Buginese },
509      {  90, PT_SC, ucp_Buhid },
510      {  96, PT_GC, ucp_C },
511      {  98, PT_SC, ucp_Canadian_Aboriginal },
512      { 118, PT_SC, ucp_Carian },
513      { 125, PT_PC, ucp_Cc },
514      { 128, PT_PC, ucp_Cf },
515      { 131, PT_SC, ucp_Chakma },
516      { 138, PT_SC, ucp_Cham },
517      { 143, PT_SC, ucp_Cherokee },
518      { 152, PT_PC, ucp_Cn },
519      { 155, PT_PC, ucp_Co },
520      { 158, PT_SC, ucp_Common },
521      { 165, PT_SC, ucp_Coptic },
522      { 172, PT_PC, ucp_Cs },
523      { 175, PT_SC, ucp_Cuneiform },
524      { 185, PT_SC, ucp_Cypriot },
525      { 193, PT_SC, ucp_Cyrillic },
526      { 202, PT_SC, ucp_Deseret },
527      { 210, PT_SC, ucp_Devanagari },
528      { 221, PT_SC, ucp_Egyptian_Hieroglyphs },
529      { 242, PT_SC, ucp_Ethiopic },
530      { 251, PT_SC, ucp_Georgian },
531      { 260, PT_SC, ucp_Glagolitic },
532      { 271, PT_SC, ucp_Gothic },
533      { 278, PT_SC, ucp_Greek },
534      { 284, PT_SC, ucp_Gujarati },
535      { 293, PT_SC, ucp_Gurmukhi },
536      { 302, PT_SC, ucp_Han },
537      { 306, PT_SC, ucp_Hangul },
538      { 313, PT_SC, ucp_Hanunoo },
539      { 321, PT_SC, ucp_Hebrew },
540      { 328, PT_SC, ucp_Hiragana },
541      { 337, PT_SC, ucp_Imperial_Aramaic },
542      { 354, PT_SC, ucp_Inherited },
543      { 364, PT_SC, ucp_Inscriptional_Pahlavi },
544      { 386, PT_SC, ucp_Inscriptional_Parthian },
545      { 409, PT_SC, ucp_Javanese },
546      { 418, PT_SC, ucp_Kaithi },
547      { 425, PT_SC, ucp_Kannada },
548      { 433, PT_SC, ucp_Katakana },
549      { 442, PT_SC, ucp_Kayah_Li },
550      { 451, PT_SC, ucp_Kharoshthi },
551      { 462, PT_SC, ucp_Khmer },
552      { 468, PT_GC, ucp_L },
553      { 470, PT_LAMP, 0 },
554      { 473, PT_SC, ucp_Lao },
555      { 477, PT_SC, ucp_Latin },
556      { 483, PT_SC, ucp_Lepcha },
557      { 490, PT_SC, ucp_Limbu },
558      { 496, PT_SC, ucp_Linear_B },
559      { 505, PT_SC, ucp_Lisu },
560      { 510, PT_PC, ucp_Ll },
561      { 513, PT_PC, ucp_Lm },
562      { 516, PT_PC, ucp_Lo },
563      { 519, PT_PC, ucp_Lt },
564      { 522, PT_PC, ucp_Lu },
565      { 525, PT_SC, ucp_Lycian },
566      { 532, PT_SC, ucp_Lydian },
567      { 539, PT_GC, ucp_M },
568      { 541, PT_SC, ucp_Malayalam },
569      { 551, PT_SC, ucp_Mandaic },
570      { 559, PT_PC, ucp_Mc },
571      { 562, PT_PC, ucp_Me },
572      { 565, PT_SC, ucp_Meetei_Mayek },
573      { 578, PT_SC, ucp_Meroitic_Cursive },
574      { 595, PT_SC, ucp_Meroitic_Hieroglyphs },
575      { 616, PT_SC, ucp_Miao },
576      { 621, PT_PC, ucp_Mn },
577      { 624, PT_SC, ucp_Mongolian },
578      { 634, PT_SC, ucp_Myanmar },
579      { 642, PT_GC, ucp_N },
580      { 644, PT_PC, ucp_Nd },
581      { 647, PT_SC, ucp_New_Tai_Lue },
582      { 659, PT_SC, ucp_Nko },
583      { 663, PT_PC, ucp_Nl },
584      { 666, PT_PC, ucp_No },
585      { 669, PT_SC, ucp_Ogham },
586      { 675, PT_SC, ucp_Ol_Chiki },
587      { 684, PT_SC, ucp_Old_Italic },
588      { 695, PT_SC, ucp_Old_Persian },
589      { 707, PT_SC, ucp_Old_South_Arabian },
590      { 725, PT_SC, ucp_Old_Turkic },
591      { 736, PT_SC, ucp_Oriya },
592      { 742, PT_SC, ucp_Osmanya },
593      { 750, PT_GC, ucp_P },
594      { 752, PT_PC, ucp_Pc },
595      { 755, PT_PC, ucp_Pd },
596      { 758, PT_PC, ucp_Pe },
597      { 761, PT_PC, ucp_Pf },
598      { 764, PT_SC, ucp_Phags_Pa },
599      { 773, PT_SC, ucp_Phoenician },
600      { 784, PT_PC, ucp_Pi },
601      { 787, PT_PC, ucp_Po },
602      { 790, PT_PC, ucp_Ps },
603      { 793, PT_SC, ucp_Rejang },
604      { 800, PT_SC, ucp_Runic },
605      { 806, PT_GC, ucp_S },
606      { 808, PT_SC, ucp_Samaritan },
607      { 818, PT_SC, ucp_Saurashtra },
608      { 829, PT_PC, ucp_Sc },
609      { 832, PT_SC, ucp_Sharada },
610      { 840, PT_SC, ucp_Shavian },
611      { 848, PT_SC, ucp_Sinhala },
612      { 856, PT_PC, ucp_Sk },
613      { 859, PT_PC, ucp_Sm },
614      { 862, PT_PC, ucp_So },
615      { 865, PT_SC, ucp_Sora_Sompeng },
616      { 878, PT_SC, ucp_Sundanese },
617      { 888, PT_SC, ucp_Syloti_Nagri },
618      { 901, PT_SC, ucp_Syriac },
619      { 908, PT_SC, ucp_Tagalog },
620      { 916, PT_SC, ucp_Tagbanwa },
621      { 925, PT_SC, ucp_Tai_Le },
622      { 932, PT_SC, ucp_Tai_Tham },
623      { 941, PT_SC, ucp_Tai_Viet },
624      { 950, PT_SC, ucp_Takri },
625      { 956, PT_SC, ucp_Tamil },
626      { 962, PT_SC, ucp_Telugu },
627      { 969, PT_SC, ucp_Thaana },
628      { 976, PT_SC, ucp_Thai },
629      { 981, PT_SC, ucp_Tibetan },
630      { 989, PT_SC, ucp_Tifinagh },
631      { 998, PT_SC, ucp_Ugaritic },
632      { 1007, PT_SC, ucp_Vai },
633      { 1011, PT_ALNUM, 0 },
634      { 1015, PT_PXSPACE, 0 },
635      { 1019, PT_SPACE, 0 },
636      { 1023, PT_WORD, 0 },
637      { 1027, PT_SC, ucp_Yi },
638      { 1030, PT_GC, ucp_Z },
639      { 1032, PT_PC, ucp_Zl },
640      { 1035, PT_PC, ucp_Zp },
641      { 1038, PT_PC, ucp_Zs }
642  };  };
643    
644  const int _pcre_utt_size = sizeof(_pcre_utt)/sizeof(ucp_type_table);  const int PRIV(utt_size) = sizeof(PRIV(utt)) / sizeof(ucp_type_table);
645    
646  #endif  /* SUPPORT_UTF8 */  #endif /* SUPPORT_UTF */
647    
648  /* End of pcre_tables.c */  /* End of pcre_tables.c */

Legend:
Removed from v.236  
changed lines
  Added in v.1015

  ViewVC Help
Powered by ViewVC 1.1.5